Closed erikbern closed 6 years ago
Code is a bit slower and a bit more bloated, but I've tested this extensively not just with unit tests but also real world applications, and it works much better.
Think I can clean up the regression models and remove a lot of redundancy also.
Will do some more cleanup later
This changes a bunch of stuff
nan
etctf.igamma
has a bug in the gradient wrta
(I'll open an issue withtensorflow
later). Rather than setting it using gradient descent, do a minor perturbation after each step